Improving model accuracy using optimal linear combinations of trained neural networks

By S. Hashem, Bruce W. Schmeiser. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, methodology): “PU-MPCNNs have become essential for many contest-winning FNNs (Sec. 5.21, Sec. 5.22). Multi-Column (MC)GPU-MPCNNs (Ciresan et al., 2011b) are committees (Breiman, 1996; Schapire, 1990; Wolpert, 1992; Hashem and Schmeiser, 1992; Ueda, 2000; Dietterich, 2000a) of GPU-MPCNNs with simple democratic outp”
On Combining Classifiers (1998, background): “The combination of ensembles of neural networks (based on different initialisations), has been studied in the neural network literature, e.g., [11], [4], [5], [10], [15], [18].”
Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition (2011, methodology): “Forecast combination has also been introduced in the neural network field (see Hashem, 1993; Hashem & Schmeiser, 1995).”
Multi-column deep neural network for traffic sign classification (2012, methodology): “For handwritten digits it was shown (Meier et al., 2011), that simply averaging the outputs of many DNN generalizes better on the test set than a combination of all the DNN with weights over a set ( Hashem & Schmeiser, 1995 ; Ueda, 2000).”
Neural networks for classification: a survey (2000, methodology): “But combining can also be done with weighted averaging that treats the contribution or accuracy of component classifiers differently [68], [67], [84].”
A theoretical and experimental analysis of linear combiners for multiple classifier systems (2005, background): “Of the various combining rules proposed in the literature, linear combiners are the most frequently used [22], [12], [2], [30], [16], [31], [32], [28], [20], [19].”